PreToolUse

A pre-action safety check for an AI coding agent. It examines file changes and shell commands before they run, blocking certain writes and dangerous commands.

In plain words
What is it for?
Use it to restrict Write and Edit operations to project files, block edits to wiki files, and reject commands such as force-pushing, hard resets, or recursive deletion.
Why use it?
It helps prevent changes outside the project and commands that could delete data, overwrite history, weaken permissions, or affect system files.

Hook for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add hooks/rbah31/claude-code-workflow/pre-tool-use
Clone the repo
git clone --depth 1 https://github.com/rbah31/claude-code-workflow

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan D 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade D, and why

PreToolUse scanned grade D with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the commands this hook runs, not an audit. A hook is shell that executes on your machine at the event it names, which is why every command in it is printed with what was found.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

"command": "CMD=$(python3 -c \"import json,sys; print(json.load(sys.stdin).get('tool_input',{}).get('command',''))\" 2>/dev/null); for PATTERN in 'rm -rf /' 'rm -rf ~' 'git push --force' 'git push -f' 'git reset --hard'

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

"command": "CMD=$(python3 -c \"import json,sys; print(json.load(sys.stdin).get('tool_input',{}).get('command',''))\" 2>/dev/null); for PATTERN in 'rm -rf /' 'rm -rf ~' 'git push --force' 'git push -f' 'git reset --hard'
.claude/settings.json · 30 lines

What it actually says

{
  "PreToolUse": [
    {
      "matcher": "Write|Edit",
      "hooks": [
        {
          "type": "command",
          "command": "FILE=$(python3 -c \"import json,sys; print(json.load(sys.stdin).get('tool_input',{}).get('file_path',''))\" 2>/dev/null); case \"$FILE\" in /etc/*|/usr/*|/var/*|/System/*|$HOME/.ssh/*|$HOME/.aws/*) echo \"BLOCKED: write outside project directory\" && exit 1;; esac; exit 0"
        },
        {
          "type": "command",
          "command": "python3 \"$CLAUDE_PROJECT_DIR/.claude/hooks/block_wiki_write.py\""
        }
      ]
    },
    {
      "matcher": "Bash",
      "hooks": [
        {
          "type": "command",
          "command": "CMD=$(python3 -c \"import json,sys; print(json.load(sys.stdin).get('tool_input',{}).get('command',''))\" 2>/dev/null); for PATTERN in 'rm -rf /' 'rm -rf ~' 'git push --force' 'git push -f' 'git reset --hard' 'chmod 777' 'mkfs' 'dd if=' 'shutdown' 'reboot'; do echo \"$CMD\" | grep -qF \"$PATTERN\" && echo \"BLOCKED: $PATTERN detected\" && exit 1; done; exit 0"
        },
        {
          "type": "command",
          "command": "python3 \"$CLAUDE_PROJECT_DIR/.claude/hooks/protect-uncommitted-hook.py\""
        }
      ]
    }
  ]
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 30 lines scan D 229cc30db008

Subscribe to this mod's changes

PreToolUse is a hook published in the GitHub repository rbah31/claude-code-workflow (5 stars, last pushed 2mo ago), licensed Apache-2.0. Its token cost is not measured: a hook is shell that never enters the context. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.